Dacheng Tao

SCE: A Manifold Regularized Set-Covering Method for Data Partitioning

2017 · IEEE Transactions on Neural Networks and Learning Systems

Cluster analysis plays a very important role in data analysis. In these years, cluster ensemble, as a cluster analysis tool, has drawn much attention for its robustness, stability, and accuracy. Many efforts have been done …

Domain Generalization via Conditional Invariant Representation

2018 · arXiv (Cornell University)

Domain generalization aims to apply knowledge gained from multiple labeled source domains to unseen target domains. The main difficulty comes from the dataset bias: training data and test data have different distributions, and the training …

Enhancing the Robustness of Neural Collaborative Filtering Systems Under Malicious Attacks

2018 · IEEE Transactions on Multimedia

Recommendation systems have become ubiquitous in online shopping in recent decades due to their power in reducing excessive choices of customers and industries. Recent collaborative filtering methods based on the deep neural network are studied …

Adversarial Examples for Hamming Space Search

2018 · IEEE Transactions on Cybernetics

Due to its strong representation learning ability and its facilitation of joint learning for representation and hash codes, deep learning-to-hash has achieved promising results and is becoming increasingly popular for the large-scale approximate nearest neighbor …

BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering

2019 · arXiv (Cornell University)

Multi-hop reasoning question answering requires deep comprehension of relationships between various documents and queries. We propose a Bi-directional Attention Entity Graph Convolutional Network (BAG), leveraging relationships between nodes in an entity graph and attention information …

Targeted Physical-World Attention Attack on Deep Learning Models in Road Sign Recognition

2020 · arXiv (Cornell University)

Real world traffic sign recognition is an important step towards building autonomous vehicles, most of which highly dependent on Deep Neural Networks (DNNs). Recent studies demonstrated that DNNs are surprisingly susceptible to adversarial examples. Many …

Structure-Aware Feature Generation for Zero-Shot Learning

2021 · arXiv (Cornell University)

Zero-Shot Learning (ZSL) targets at recognizing unseen categories by leveraging auxiliary information, such as attribute embedding. Despite the encouraging results achieved, prior ZSL approaches focus on improving the discriminant power of seen-class features, yet have …

Hierarchical Prototype Networks for Continual Graph Representation Learning

2022 · IEEE Transactions on Pattern Analysis and Machine Intelligence

Despite significant advances in graph representation learning, little attention has been paid to the more practical continual learning scenario in which new categories of nodes (e.g., new research areas in citation networks, or new types …

Knowledge Graph Augmented Network Towards Multiview Representation Learning for Aspect-based Sentiment Analysis

2022 · arXiv (Cornell University)

Aspect-based sentiment analysis (ABSA) is a fine-grained task of sentiment analysis. To better comprehend long complicated sentences and obtain accurate aspect-specific information, linguistic and commonsense knowledge are generally required in this task. However, most current …

BLISS: Robust Sequence-to-Sequence Learning via Self-Supervised Input Representation

2022 · arXiv (Cornell University)

Data augmentations (DA) are the cores to achieving robust sequence-to-sequence learning on various natural language processing (NLP) tasks. However, most of the DA approaches force the decoder to make predictions conditioned on the perturbed input …

Few-shot Backdoor Defense Using Shapley Estimation

2021 · arXiv (Cornell University)

Deep neural networks have achieved impressive performance in a variety of tasks over the last decade, such as autonomous driving, face recognition, and medical diagnosis. However, prior works show that deep neural networks are easily …

Spectral complexity-scaled generalization bound of complex-valued neural networks

2023 · Edinburgh Research Explorer (University of Edinburgh)

Complex-valued neural networks (CVNNs) have been widely applied in various fields, primarily in signal processing and image recognition. Few studies have focused on the generalisation of CVNNs, although it is vital to ensure the performance …

Not All Instances Contribute Equally: Instance-adaptive Class Representation Learning for Few-Shot Visual Recognition

2022 · arXiv (Cornell University)

Few-shot visual recognition refers to recognize novel visual concepts from a few labeled instances. Many few-shot visual recognition methods adopt the metric-based meta-learning paradigm by comparing the query representation with class representations to predict the …

Instructed Diffuser with Temporal Condition Guidance for Offline Reinforcement Learning

2023 · arXiv (Cornell University)

Recent works have shown the potential of diffusion models in computer vision and natural language processing. Apart from the classical supervised learning fields, diffusion models have also shown strong competitiveness in reinforcement learning (RL) by …

Structured Cooperative Learning with Graphical Model Priors

2023 · arXiv (Cornell University)

We study how to train personalized models for different tasks on decentralized devices with limited local data. We propose "Structured Cooperative Learning (SCooL)", in which a cooperation graph across devices is generated by a graphical …

A Comprehensive Survey of Dataset Distillation

2023 · IEEE Transactions on Pattern Analysis and Machine Intelligence

Deep learning technology has developed unprecedentedly in the last decade and has become the primary choice in many application domains. This progress is mainly attributed to a systematic collaboration in which rapidly growing computing resources …

Unified Domain Adaptive Semantic Segmentation

2023 · arXiv (Cornell University)

Unsupervised Domain Adaptive Semantic Segmentation (UDA-SS) aims to transfer the supervision from a labeled source domain to an unlabeled target domain. The majority of existing UDA-SS works typically consider images whilst recent attempts have extended …

Stochastic Optimization for Nonconvex Problem With Inexact Hessian Matrix, Gradient, and Function

2023 · IEEE Transactions on Neural Networks and Learning Systems

Trust region (TR) and adaptive regularization using cubics (ARC) have proven to have some very appealing theoretical properties for nonconvex optimization by concurrently computing function value, gradient, and Hessian matrix to obtain the next search …

Joint Input and Output Coordination for Class-Incremental Learning

2024 · arXiv (Cornell University)

Incremental learning is nontrivial due to severe catastrophic forgetting. Although storing a small amount of data on old tasks during incremental learning is a feasible solution, current strategies still do not 1) adequately address the …

Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging

2025 · IEEE Transactions on Pattern Analysis and Machine Intelligence

Multi-task learning (MTL) leverages a shared model to accomplish multiple tasks and facilitate knowledge transfer. Recent research on task arithmetic-based MTL demonstrates that merging the parameters of independently fine-tuned models can effectively achieve MTL. However, …

AD-FM: Multimodal LLMs for Anomaly Detection via Multi-Stage Reasoning and Fine-Grained Reward Optimization

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities across diverse domains, their application to specialized anomaly detection (AD) remains constrained by domain adaptation challenges. Existing Group Relative Policy Optimization (GRPO) based approaches suffer from …

Offline Behavioral Data Selection

2026

Behavioral cloning is a widely adopted approach for offline policy learning from expert demonstrations. However, the large scale of offline behavioral datasets often results in computationally intensive training when used in downstream tasks. In this …

Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT

2023 · arXiv (Cornell University)

Recently, ChatGPT has attracted great attention, as it can generate fluent and high-quality responses to human inquiries. Several prior studies have shown that ChatGPT attains remarkable generation ability compared with existing models. However, the quantitative …